Intelligent spectrum management is crucial for improving spectrum efficiency and achieving secure utilization of spectrum resources. However, existing intelligent spectrum management methods, typically based on small-scale models, suffer from notable limitations in recognition accuracy, convergence speed, and generalization, particularly in the complex and dynamic spectrum environments. To address these challenges, this paper proposes a novel spectrum foundation model, termed SpectrumFM, establishing a new paradigm for spectrum management. SpectrumFM features an innovative encoder architecture that synergistically exploits the convolutional neural networks and the multi-head self-attention mechanisms to enhance feature extraction and enable robust representation learning. The model is pre-trained via two novel self-supervised learning tasks, namely masked reconstruction and next-slot signal prediction, which leverage large-scale in-phase and quadrature (IQ) data to achieve comprehensive and transferable spectrum representations. Furthermore, a parameter-efficient fine-tuning strategy is proposed to enable SpectrumFM to adapt to various downstream spectrum management tasks, including automatic modulation classification (AMC), wireless technology classification (WTC), spectrum sensing (SS), and anomaly detection (AD). Extensive experiments demonstrate that SpectrumFM achieves superior performance in terms of accuracy, robustness, adaptability, few-shot learning efficiency, and convergence speed, consistently outperforming conventional methods across multiple benchmarks. Specifically, SpectrumFM improves AMC accuracy by up to 12.1% and WTC accuracy by 9.3%, achieves an area under the curve (AUC) of 0.97 in SS at -4 dB signal-to-noise ratio (SNR), and enhances AD performance by over 10%.

Semantic communication has shown exceptional performance in various tasks, such as image classification, owing to the advancements in deep learning technologies. However, due to the openness of wireless channels and the vulnerability of neural networks, semantic communication faces significant challenges from semantic impairment in the physical channel. In this paper, semantic impairment refers to the minor perturbations that cause discrepancies between the received features and the expected ones, which can lead to errors in image classification. We design four constraints from the perspectives of semantic level, concealment level and efficiency level to simulate potential malicious semantic impairment. These constraints are employed to generate adversarial perturbations specifically targeting semantic communication systems, ensuring that the perturbations can more effectively disrupt the normal function of the systems. Moreover, we innovatively propose knowledge graph enhanced anti-impairment cognitive semantic communication, which combines knowledge graph and adversarial training to boost robustness against semantic impairment. Specifically, we leverage the shared knowledge graph to transmit triplet information from the transmitter to the receiver in the form of indices and introduce the triplet information as additional information into the decoder to facilitate the decoding process. Simulation results show that our proposed knowledge graph enhanced cognitive semantic communication system achieves higher classification accuracy and robustness in environments with low signal-to-noise ratio and semantic impairment, compared to existing Better Portable Graphics (BPG) and Joint Source-Channel Coding(JSCC) schemes.

The enhancement of spectrum efficiency and the realization of secure spectrum utilization are critically dependent on spectrum cognition. However, existing spectrum cognition methods often exhibit limited generalization and suboptimal accuracy when deployed across diverse spectrum environments and tasks. To overcome these challenges, we propose a spectrum foundation model, termed SpectrumFM, which provides a new paradigm for spectrum cognition. An innovative spectrum encoder that exploits the convolutional neural networks and the multi-head self attention mechanisms is proposed to effectively capture both fine-grained local signal structures and high-level global dependencies in the spectrum data. To enhance its adaptability, two novel self-supervised learning tasks, namely masked reconstruction and next-slot signal prediction, are developed for pre-training SpectrumFM, enabling the model to learn rich and transferable representations. Furthermore, low-rank adaptation (LoRA) parameter-efficient fine-tuning is exploited to enable SpectrumFM to seamlessly adapt to various downstream spectrum cognition tasks, including spectrum sensing (SS), anomaly detection (AD), and wireless technology classification (WTC). Extensive experiments demonstrate the superiority of SpectrumFM over state-of-the-art methods. Specifically, it improves detection probability in the SS task by 30% at -4 dB signal-to-noise ratio (SNR), boosts the area under the curve (AUC) in the AD task by over 10%, and enhances WTC accuracy by 9.6%.1

Semantic communication is envisioned as a potential communication paradigm enabled by artificial intelligence and is promising to break the Shannon limit for future 6G networks. This paradigm benefits uninhabited aerial vehicles (UAVs) to conserve communication resources and minimize latency by only transmitting task-relevant semantic information. However, resource allocation in the multiple collaborative UAV scenarios remains unexplored, particularly regarding multi-modal semantic communication. To tackle this challenge, this paper investigates a semantic-aware intelligent resource allocation method for multi-UAV-assisted semantic communication networks in the UAV image-sensing task-oriented scenario. A multi-modal semantic communication framework with multi-UAV relay collaboration is developed. At the semantic level, a novel quality of experience (QoE) and the transmission cost model are introduced, based on which a semantic-aware resource allocation problem is formulated, aiming to maximize QoE while minimizing the transmission cost by jointly optimizing the UAV trajectory, the spectrum bandwidth, the transmit power and the number of the transmitted semantic symbols. To deal with optimization challenges involving hybrid variables and coordination among UAVs, a multi-UAV hybrid decision-controlled deep reinforcement learning (DRL) scheme is proposed. Simulation results demonstrate the effectiveness of the proposed scheme compared with the benchmark schemes in achieving a good balance between the QoE and the transmission cost.

Learning-task oriented semantic communication is pivotal in optimizing transmission efficiency by extracting and conveying essential semantics tailored to the specific tasks, such as image reconstruction and classification. Nevertheless, the challenge of eavesdropping poses a formidable threat to semantic privacy due to open nature of wireless communications. In this paper, intelligent reflective surface (IRS)-enhanced secure semantic communication (IRS-SSC) is proposed to guarantee the physical layer security from a task-oriented semantic perspective. Specifically, a multi-layer codebook is exploited to discretize continuous semantic features and describe semantics with different numbers of bits, thereby meeting the need for hierarchical semantic representation and further enhancing the transmission efficiency. Novel semantic security metrics, i.e., secure semantic rate (S-SR) and secure semantic spectrum efficiency (S-SSE), are defined to map the task-oriented security requirements at the application layer into the physical layer. To achieve artificial intelligence (AI)-native secure communication, we propose a noise disturbance enhanced hybrid deep reinforcement learning (NdeHDRL)-based resource allocation scheme. This scheme dynamically maximizes the S-SSE by jointly optimizing the bits for semantic representations, reflective coefficients of the IRS, and the subchannel assignment. Moreover, we propose a novel semantic context awared state space (SCA-SS) to fusion the high-dimensional semantic space and the observable system state space, which enables the agent to perceive semantic context and solves the dimensional catastrophe problem. Simulation results demonstrate the efficiency of our proposed schemes in both enhancing the security performance and the S-SSE compared to several benchmark schemes.

Semantic communication is a promising approach to address the challenge of limited spectrum resources in the sixth-generation (6G) communication networks. However, prior works on semantic communication focus primarily on semantic coding, and they do not investigate how to efficiently construct a semantic knowledge base. In this paper, a codebook-based unified hierarchical semantic knowledge base (UH-SKB) framework is studied for multi-task semantic communications. To maximize semantic representation spaces and effectively explore the semantic relevance among multiple tasks, the semantic knowledge base is constructed jointly in both the horizontal and vertical directions. A deep K-subspace cluster method is proposed to facilitate semantic relevance extraction and semantic subspace construction for high-dimensional semantic information. Simulation results demonstrate that the proposed UH-SKB can support multi-task semantic communications efficiently, achieving up to 13.4%, 14% and 6.3% performance improvement respectively for reconstruction, segmentation and classification tasks compared to standalone semantic knowledge bases at the novel dataset when SNR is 0 dB. Moreover, the proposed UH-SKB exhibits 95.3% knowledge search efficiency improvement on the reconstruction task compared to standalone semantic knowledge bases.

In this paper, we propose an adaptive semantic resource allocation paradigm with semantic-bit quantization (SBQ) compatible with existing wireless communications, where the inaccurate environment perception introduced by the additional mapping relationship between semantic metrics and transmission metrics is solved. Specifically, SBQ is a hybrid uniform-non-uniform quantization method, which aims to facilitate the coding between semantics and bits. In order to investigate the performance of semantic communication networks, the quality of service for semantic communication (SC-QoS), including the semantic quantization efficiency (SQE) and transmission latency, is proposed for the first time. A problem of maximizing the overall effective SC-QoS is formulated by jointly optimizing the transmit beamforming of the base station, the bits for semantic representation, the subchannel assignment, and the bandwidth resource allocation. To address the non-convex formulated problem, an intelligent resource allocation scheme is proposed based on a hybrid deep reinforcement learning (DRL) algorithm, where the intelligent agent can perceive both semantic tasks and dynamic wireless environments. Simulation results demonstrate that our design can effectively combat semantic noise and achieve superior performance in wireless communications compared to several benchmark schemes. Furthermore, compared to mapping-guided paradigm based resource allocation schemes, our proposed adaptive scheme can achieve up to 13% performance improvement in terms of SC-QoS.

Recommendation systems are of crucial importance due to their wide applications. Knowledge graph (KG) enabled recommendation schemes have attracted great attention due to their superior performance and interpretability. However, the rich social information is not exploited for those systems, which limits the recommendation performance . In this paper, a novel explainable recommendation scheme is proposed by exploiting our designed social enhanced knowledge graph attention network (SKGAN). The hidden relations among users and items are learned and used for recommendation with the collaborative KG (CKG) and the user social graph (USG). Moreover, the high-order semantic information in both CKG and USG are obtained by using the graph convolution networks (GCNs) and the node level attention algorithm. Furthermore, a graph level user-specific attention algorithm is proposed to capture the user personalized preference between CKG and USG. Extensive experiment results demonstrate that normalized discounted cumulative gain (NDCG), precision, recall and hits ratio (HR) achieved with our proposed recommendation system are the best among those obtained with the state-of-the-art benchmark recommendation systems.

Secure communications are of paramount importance in spectrum sharing networks due to the allocation and sharing characteristics of spectrum resources. To further explore the potential of intelligent reflective surfaces (IRSs) in enhancing spectrum sharing and secure transmission performance, a multiple intelligent reflection surface (multi-IRS)-assisted sensing-enhanced wideband spectrum sharing network is investigated by considering physical layer security techniques. An intelligent resource allocation scheme based on double deep Q networks (D3QN) algorithm and soft Actor-Critic (SAC) algorithm is proposed to maximize the secure transmission rate of the secondary network by jointly optimizing IRS pairings, subchannel assignment, transmit beamforming of the secondary base station, reflection coefficients of IRSs and the sensing time. To tackle the sparse reward problem caused by a significant amount of reflection elements of multiple IRSs, the method of hierarchical reinforcement learning is exploited. An alternative optimization (AO)-based conventional mathematical scheme is introduced to verify the computational complexity advantage of our proposed intelligent scheme. Simulation results demonstrate the efficiency of our proposed intelligent scheme as well as the superiority of multi-IRS design in enhancing secrecy rate and spectrum utilization. It is shown that inappropriate deployment of IRSs can reduce the security performance with the presence of multiple eavesdroppers (Eves), and the arrangement of IRSs deserves further consideration.

Spectrum sensing and communication security are of crucial importance in cognitive radio networks (CRNs). In this paper, we utilize intelligent reflecting surfaces (IRS) to simultaneously enhance spectrum sensing accuracy and the secrecy performance of secondary users (SUs) through physical layer security (PLS) techniques. Additionally, we employ IRS as a novel approach to achieve the target probability of detection. We formulate a joint sensing and transmission security optimization problem to maximize the sum secrecy rate of SUs under both perfect and imperfect channel state information (CSI). To transform the probability of detection into a tractable expression, we adopt a safe approximation for theQ-function. We use a computationally-efficient block coordinate descent (BCD)-based algorithm to optimize the beamforming design and IRS phase shifts alternately. Specifically, we employ theS-procedure to handle the semi-infinite constraints under the imperfect CSI case. Simulation results demonstrate that by leveraging IRS for spectrum sensing, we can significantly reduce the sensing time while achieving the required probability of detection and the probability of false alarm. Furthermore, our proposed scheme improves both sensing accuracy and secrecy rate in both cases compared to the benchmark schemes.

Spectrum sharing is promising as a solution to address the spectrum crunch by enabling the coexistence of different networks in the same frequency band. However, interference from concurrent transmissions remains an obstacle to further enhance spectral efficiency. Therefore, to overcome the bottleneck caused by multi-user interference, both rate-splitting multiple access (RSMA)-enabled underlay and overlay spectrum-sharing strategies are proposed in this paper. To facilitate a robust resource allocation design, the common and the private beamforming vectors as well as the common rate allocation are jointly optimized under the norm-bounded channel state information (CSI) error model to maximize the worst-case weighted sum rate (WSR) of the secondary networks. To address the formulated challenging non-convex quadratically-constrained resource allocation optimization problems, a computationally efficient successive convex approximation (SCA)-based algorithm capitalizing on semidefinite relaxation (SDR) is proposed. Simulation results demonstrate that the proposed algorithms outperform non-orthogonal multiple access (NOMA)-based benchmark schemes in worst-case WSR and robustness. Moreover, the results indicate that the proposed novel RSMA-enabled overlay spectrum-sharing strategy can offer a higher flexibility in resource allocation compared to their underlay counterparts. Furthermore, the tradeoff between interference management and spectral performance enhancement for the proposed RSMA-enabled overlay spectrum-sharing strategy is unveiled.

Semantic communication is envisioned as a potential communication paradigm based on artificial intelligence that holds the promise of breaking the Shannon limit for future 6G networks. This paradigm offers a promising opportunity for Unmanned Aerial Vehicles (UAVs) to conserve communication resources and minimize latency by only transmitting relevant semantic information. Despite the promising potential of UAV semantic communication networks, resource allocation in this context remains largely unexplored, particularly regarding multi-modal communication that adjusts the types of transmitted information (image, text, video, etc.) according to the task objectives and the available resources. This paper addresses the semantic-oriented resource allocation for multi-modal semantic communication with a focus on the UAV image-sensing task-oriented scenario. Firstly, a multi-modal semantic communication for the original image-sensing tasks of UAVs is designed. Subsequently, a semantic-level resource allocation problem based on the approximate semantic entropy and the semantic rate is formulated in terms of the transmit power allocation, channel assignment, and the number of transmitted semantic symbols. To solve the problem formulated, which involves a hybrid discrete-continuous action space, a novel algorithm called Hybrid-Decision-Controlled Deep Reinforcement Learning-based Semantic Communication Allocation (HDCD-SC) is introduced. The simulation results demonstrate that the proposed HDCD-SC algorithm can dynamically adjust the transmission modal according to the available resources, and achieve better performance in terms of latency, amount of semantic information, and notable reductions in energy and bandwidth costs when compared to other benchmarks.

Spectrum sensing and the communication security are of crucial importance in cognitive radio networks (CRNs). In this paper, intelligent reflecting surface (IRS) is exploited in CRNs to simultaneously enhance the spectrum sensing accuracy and the secure performance achieved by using physical layer security (PLS) techniques. The sum secrecy rate of the secondary users (SUs) is maximized by jointly optimizing the sensing time, the beamforming design and the IRS phase shifts. A safe approximation is adopted to transform the probability of detection into a tractable expression. A computationally efficient block coordinate descent (BCD)-based algorithm with the techniques of successive convex approximation (SCA) and semidefinite relaxation (SDR) is exploited to optimize the beamforming and the phase shifts alternately. Simulation results demonstrate that our proposed algorithm can significantly improve both the sensing performance and the secrecy rate compared with the benchmark schemes.

Cognitive radio (CR) is one of the most disruptive techniques for enabling the next generation wireless communication networks due to its potential in improving the spectral efficiency. In this paper, intelligent reflecting surface (IRS) is exploited to enhance both the accuracy of spectrum sensing and the secondary transmission in a CR network (CRN) employing the opportunistic spectrum access. A novel detection threshold based on the probability of false alarm is derived for improving the spectrum sensing performance. The average achievable rate of the secondary network is maximized under both the two-stage and one-stage IRS phase shifts case. To tackle the challenging non-convex optimization problem under the two-stage case, a computationally efficient block coordinate descent (BCD)-based algorithm is proposed coputilizing the techniques of successive convex approximation (SCA) and semidefinite relaxation (SDR). Moreover, a BCD method and a tractable approximation of the probability of detection are exploited to tackle the problem under one-stage IRS phase shifts case. Simulation results demonstrate that our proposed designs are superior to the benchmark schemes in terms of the achievable rate and the sensing performance, and IRS can greatly improve the spectral efficiency of the CRN.

Orthogonal frequency division multiplexing (OFDM) systems have been widely applied in practice since OFDM has diverse outstanding advantages. However, their performance improvement is confronted with bottlenecks. In this paper, in order to tackle this issue, intelligent resource allocation driven by reinforcement learning is studied in intelligent reflecting surface (IRS) enhanced OFDM systems. The system sum rate is maximized by jointly optimizing the subcarrier allocation, the transmit beamforming of the base station and the phase shift of the IRS. An intelligent resource allocation scheme based on combining deep Q networks (DQN) and deep deterministic policy-gradient (DDPG) is proposed to tackle the formulated challenging non-convex problems. In order to further improve the spectrum efficiency, spectrum sharing is considered in the IRS-enhanced OFDM system. The secondary users sum rate maximization framework is formulated by jointly optimizing the channel allocation, the transmit beamforming of the secondary base station (SBS) and the phase shift of the IRS. Dueling double deep Q networks (D3QN) and twin delayed deep deterministic policy gradient (TD3) are exploited to tackle the hybrid action space issue under interference. Simulation results demonstrate that our proposed schemes can significantly improve the transmission rate compared to the benchmark schemes.

Cognitive radio (CR) is one of the most disruptive techniques for enabling the next generation wireless communication networks due to its potential in improving the spectral efficiency. In this paper, an intelligent reflecting surface (IRS) is exploited to assist both spectrum sensing and secondary transmission in the CR network (CRN) employing opportunistic spectrum access. A novel IRS-enhanced spectrum sensing scheme and a redesigned detection threshold are proposed to improve the sensing performance. We formulate the throughput maximization problem by jointly optimizing the sensing time, the beamforming, and the IRS phase shifts. A computationally efficient block coordinate descent (BCD)-based algorithm is proposed to tackle the non-convex problem. Simulation results show that our proposed scheme is superior to other benchmark schemes in terms of both the throughput and the sensing performance.

In this paper, we study the resource allocation problem for an intelligent reflecting surface (IRS)-assisted OFDM system. The system sum rate maximization framework is formulated by jointly optimizing subcarrier allocation, base station transmit beamforming and IRS phase shift. Considering the continuous and discrete hybrid action space characteristics of the optimization variables, we propose an efficient resource allocation algorithm combining multiple deep Q networks (MDQN) and deep deterministic policy-gradient (DDPG) to deal with this issue. In our algorithm, MDQN are employed to solve the problem of large discrete action space, while DDPG is introduced to tackle the continuous action allocation. Compared with the traditional approaches, our proposed MDQN-DDPG based algorithm has the advantage of continuous behavior improvement through learning from the environment. Simulation results demonstrate superior performance of our design in terms of system sum rate compared with the benchmark schemes.

Non-orthogonal multiple access (NOMA) is a promising candidate for the sixth generation wireless communication networks due to its high spectrum efficiency (SE), energy efficiency (EE), and better connectivity. It can be applied in cognitive radio networks (CRNs) to further improve SE and user connectivity. However, the interference caused by spectrum sharing and the utilization of non-orthogonal resources can downgrade the achievable performance. In order to tackle this issue, intelligent reflecting surface (IRS) is exploited in a downlink multiple-input-single-output (MISO) CRN with NO-MA. To realize a desirable tradeoff between SE and EE, a multi-objective optimization (MOO) framework is formulated. An iterative block coordinate descent (BCD)-based algorithm is exploited to optimize the beamforming design and IRS reflection coefficients iteratively. Simulation results demonstrate that the proposed scheme can achieve a better balance between SE and EE than baseline schemes.

Non-orthogonal multiple access (NOMA) is a promising candidate for the sixth generation wireless communication networks due to its high spectrum efficiency (SE), energy efficiency (EE), and better connectivity. It can be applied in cognitive radio networks (CRNs) to further improve SE and user connectivity. However, the interference caused by spectrum sharing and the utilization of non-orthogonal resources can downgrade the achievable performance. In order to tackle this issue, intelligent reflecting surface (IRS) is exploited in a downlink multiple-input-single-output (MISO) CRN with NOMA. To realize a desirable tradeoff between SE and EE, a multi-objective optimization (MOO) framework is formulated under both the perfect and imperfect channel state information (CSI). An iterative block coordinate descent (BCD)-based algorithm is exploited to optimize the beamforming design and IRS reflection coefficients iteratively under the perfect CSI case. A safe approximation and the$ \mathcal {S}$-procedure are used to address the non-convex infinite inequality constraints of the problem under the imperfect CSI case. Simulation results demonstrate that the proposed scheme can achieve a better balance between SE and EE than baseline schemes. Moreover, it is shown that both SE and EE of the proposed algorithm under the imperfect CSI can be significantly improved by exploiting IRS.

Mobile edge computing (MEC) has been envisaged as a promising technique in the next-generation wireless networks. In order to improve the security of computation tasks offloading and enhance user connectivity, physical layer security and non-orthogonal multiple access (NOMA) are studied in MEC-aware networks. The secrecy outage probability is adopted to measure the secrecy performance of computation offloading by considering a practically passive eavesdropping scenario. The weighted sum-energy consumption minimization problem is firstly investigated subject to the secrecy offloading rate constraints, the computation latency constraints and the secrecy outage probability constraints. The semi-closed form expression for the optimal solution is derived. We then investigate the secrecy outage probability minimization problem by taking the priority of two users into account, and characterize the optimal secrecy offloading rates and power allocations with closed-form expressions. Numerical results demonstrate that the performance of our proposed design are better than those of the alternative benchmark schemes.

This paper considers a non-orthogonal multiple access (NOMA) assisted mobile edge computing (MEC) system in the presence of a malicious eavesdropper. We employ the partial offloading mode such that each user can divide the individual computation task into two parts for local executing and offloading, respectively. The secrecy outage probability is adopted to measure the secrecy performance of computation ofloading by considering the practically passive eavesdropping scenario. Under this setup, we investigate the problem of minimizing the weighted sum-energy consumption for all users, subject to the secrecy ofloading rates constraints, the computation latency constraints and the secrecy outage probability constraints, and then derive the semi-closed form solution for this problem. Numerical results are provided and demonstrate that the merits of our proposed design are better than those of the alternative benchmark schemes.

This paper considers a proactive eavesdropping problem, in which a full-duplex legitimate monitor aims to eavesdrop on a suspicious communication link between the secondary pairs in a cognitive radio (CR) network via jamming. For such a scenario, the jamming signals would not only disrupt the suspicious receivers, but also influences the interference received at the primary receiver, which both destroy the transmitting rate in the suspicious link. Hence, the design of the beamforming should have good tradeoff between those two affects. We aim to maximize the eavesdropping rate by designing the jamming beamforming under the transmitting power (TP) constraint at the legitimate monitor and the interference temperature (IT) constraint at the primary receiver, which is a non- convex problem. Specifically, several cases are discussed to decompose the original problem and a closed-form solution is finally presented by solving two sub-problems. In particular, some analyses on the main parameters (the maximum power at the legitimate monitor and the interference temperature at the primary receiver) are undertaken to obtain their boundaries corresponding to different modes of the optimal vector, which influence the performance of the system. Numerical results are finally presented to demonstrate the performance of our proposed schemes outperforms the reference solutions.

In this study, the authors study the max–min fairness for wireless energy transfer in a multiuser multiple‐input multiple‐output communication system with simultaneous wireless information and power transfer. In particular, they aim to maximise the minimum harvested energy among the multiple multi‐antenna energy receivers while guaranteeing secure communication for multi‐antenna information receiver. The dual use of artificial noise to facilitate both wireless energy transfer and secure communication is exploited in the authors’ proposed problem. Both scenarios of perfect and imperfect channel state information (CSI) known at the transmitter are considered. For the perfect CSI case, the formulated max–min energy harvesting (MM‐EH) problem is non‐convex and intractable. To circumvent it, an iterative optimisation algorithm based on Taylor series expansion is proposed. Then, they turn their attention to the imperfect CSI case, where a max–min robust energy harvesting (MMR‐EH) problem is considered. Though the MMR‐EH problem is more complicated than the MM‐EH problem, they reveal that the iterative optimisation method can be extended to the solution of the former, wherein the S‐procedure is introduced. Simulation results show the efficiency of their proposed solutions in terms of energy harvesting.

In this paper, a robust downlink beamforming design for simultaneous wireless information and power transfer (SWIPT) in a multiuser MISO communication system is proposed. Our design is to maximize the minimum harvested energy among the multi-antenna energy receivers (ERs) while guaranteeing the secure communication requirement at the information receiver (IR) by optimizing the transmit beamforming vectors and power splitting ratio jointly. The considered max-min fair problem is non-convex and hard to tackle. Using the semi-definite relaxation (SDR) technique, we solve this problem by carrying out a one-dimensional search which refer to the solution of a series of semi-definite programs (SDPs). Also, we provide the closed-form solution based on Lagrange duality and prove that the utilized SDR is tight. Simulation results show our proposed robust scheme is more efficient than the conventional isotropic scheme in terms of energy harvesting.